© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and governmental actions

    oai_token-act-pair · gpt-3.5-turbo

    past and present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.74
     inhabit
    -0.70
     Mam
    -0.68
     Pictures
    -0.68
     fortunes
    -0.67
    sburg
    -0.67
     Bucc
    -0.66
     souls
    -0.66
     Temper
    -0.66
     fortune
    -0.65
    POSITIVE LOGITS
     ineffective
    1.11
     designed
    1.04
     implemented
    0.99
     activated
    0.98
     administered
    0.98
     invaluable
    0.97
     meant
    0.96
     abolished
    0.95
     supposed
    0.95
     mandated
    0.94
    Activations Density 0.506%

    No Known Activations